Update upstream source from tag 'upstream/2018.04.25'

[youtubedl] / youtube_dl / extractor / vessel.py

diff --git a/youtube_dl/extractor/vessel.py b/youtube_dl/extractor/vessel.py
index 1a0ff3395598027ebd8de05a609faca987c14e9e..80a643dfe6d6a7a160cb4035b52b9a95b03769cf 100644 (file)
--- a/youtube_dl/extractor/vessel.py
+++ b/youtube_dl/extractor/vessel.py
@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import json
 from __future__ import unicode_literals
 
 import json

+import re

 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (


@@ -12,23 +13,38 @@ from ..utils import (
 
 
 class VesselIE(InfoExtractor):
 
 
 class VesselIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?vessel\.com/videos/(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z-_]+)'

     _API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s'
     _LOGIN_URL = 'https://www.vessel.com/api/account/login'
     _NETRC_MACHINE = 'vessel'
     _API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s'
     _LOGIN_URL = 'https://www.vessel.com/api/account/login'
     _NETRC_MACHINE = 'vessel'

-    _TEST = {
+    _TESTS = [{

         'url': 'https://www.vessel.com/videos/HDN7G5UMs',
         'md5': '455cdf8beb71c6dd797fd2f3818d05c4',
         'info_dict': {
             'id': 'HDN7G5UMs',
             'ext': 'mp4',
             'title': 'Nvidia GeForce GTX Titan X - The Best Video Card on the Market?',
         'url': 'https://www.vessel.com/videos/HDN7G5UMs',
         'md5': '455cdf8beb71c6dd797fd2f3818d05c4',
         'info_dict': {
             'id': 'HDN7G5UMs',
             'ext': 'mp4',
             'title': 'Nvidia GeForce GTX Titan X - The Best Video Card on the Market?',

-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',

             'upload_date': '20150317',
             'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?',
             'timestamp': int,
         },
             'upload_date': '20150317',
             'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?',
             'timestamp': int,
         },

-    }
+    }, {
+        'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.vessel.com/videos/F01_dsLj1',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.vessel.com/videos/RRX-sir-J',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [url for _, url in re.findall(
+            r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z-_]+.*?)\1',
+            webpage)]

 
     @staticmethod
     def make_json_request(url, data):
 
     @staticmethod
     def make_json_request(url, data):


@@ -98,16 +114,24 @@ class VesselIE(InfoExtractor):
 
         formats = []
         for f in video_asset.get('sources', []):
 
         formats = []
         for f in video_asset.get('sources', []):

-            if f['name'] == 'hls-index':
+            location = f.get('location')
+            if not location:
+                continue
+            name = f.get('name')
+            if name == 'hls-index':

                 formats.extend(self._extract_m3u8_formats(
                 formats.extend(self._extract_m3u8_formats(

-                    f['location'], video_id, ext='mp4', m3u8_id='m3u8'))
+                    location, video_id, ext='mp4',
+                    entry_protocol='m3u8_native', m3u8_id='m3u8', fatal=False))
+            elif name == 'dash-index':
+                formats.extend(self._extract_mpd_formats(
+                    location, video_id, mpd_id='dash', fatal=False))

             else:
                 formats.append({
             else:
                 formats.append({

-                    'format_id': f['name'],
+                    'format_id': name,

                     'tbr': f.get('bitrate'),
                     'height': f.get('height'),
                     'width': f.get('width'),
                     'tbr': f.get('bitrate'),
                     'height': f.get('height'),
                     'width': f.get('width'),

-                    'url': f['location'],
+                    'url': location,

                 })
         self._sort_formats(formats)
 
                 })
         self._sort_formats(formats)